The abstract is read at the publisher; the summary is JClub's.
Daily-Academic integrates semantic literature discovery, journal monitoring, and linked omics exploration, improving top-ranked biomedical literature over BM25 and PubMedBERT on a 259,246-publication benchmark.
- Why it matters: Biomedical researchers currently piece together alerts, manual searches, and journal portals, leaving gaps in unified, profile-driven monitoring and retrieval quality.
- What they did: The platform encodes titles and abstracts as dense semantic representations and ranks results by semantic match to an explicit, editable user profile plus recency and journal preferences; offline evaluation used 30 biomedical queries with pooled graded relevance.
- The result: Semantic representation improved retrieval quality relative to lexical and dense baselines, with differences spread across queries; because the benchmark was user-free, adaptive personalization was inactive and ranking weights were untuned.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.